Python爬虫实践 —— 6.豆瓣电影排行榜百top数据爬取

import urllib.request
import re

headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:71.0) Gecko/20100101 Firefox/71.0"}

url = "https://movie.douban.com/j/chart/top_list?type=5&interval_id=100%3A90&action=&start=0&limit=100"

res = urllib.request.Request(url, headers=headers)

data = urllib.request.urlopen(res).read().decode()

pat1=re.compile(r‘"rating":\["(.*?)","\d+"\]‘)
pat2=re.compile(r‘"title":"(.*?)"‘)

data1=pat1.findall(data, re.I)
data2=pat2.findall(data, re.I)

print(data1,data2)

for x in range(len(data1)):
    print("排名：{0} 电影名：{1} 豆瓣评分:{2}".format(x+1, data2[x], data1[x]))